Twitter Sentiment Analysis Approaches: A Survey

Authors

  • Omar Yousef Adwan The University of Jordan https://orcid.org/0000-0003-3967-2456
  • Marwan Al-Tawil The University of Jordan
  • Ammar Huneiti The University of Jordan
  • Rawan Shahin The University of Jordan
  • Abeer Abu Zayed The University of Jordan
  • Razan Al-Dibsi The University of Jordan

DOI:

https://doi.org/10.3991/ijet.v15i15.14467

Keywords:

— Data analysis, sentiment analysis, social media, twitter, machine learning, graph, survey.

Abstract


Twitter is one of the most popular microblogging and social networking platforms where massive instant messages (i.e. tweets) are posted every day. Twitter sentiment analysis tackles the problem of analyzing users’ tweets in terms of thoughts, interests and opinions in a variety of contexts and domains. Such analysis can be valuable for several researchers and applications that require understanding people views about a particular topic or event. The study carried out in this paper provides an overview of the algorithms and approaches that have been used for sentiment analysis in twitter. The reviewed articles are categories into four categories based on the approach they use. Furthermore, we discuss directions for future research on how twitter sentiment analysis approaches can utilize theories and technologies from other fields such cognitive science, semantic Web, big data and visualization.

Author Biographies

Omar Yousef Adwan, The University of Jordan

An Associate Professor with the University of Jordan, King Abdullah II School for Information Technology, Computer Information Systems Department. Dr. Omar holds a B.Sc in Computer Science (Eastern Michigan University, 1987) and a M.Sc. in Computer Science (The George Washington University, 1998), and a Ph.D in Computer Science (The George Washington University, 2008). He served as a chairman to CIS Dept. of KASIT during 2012-2016. His current areas of interest include: Software Engineering, System Engineering Tools, and Databases.

Marwan Al-Tawil, The University of Jordan

Marwan Al-Tawil is currently an Assistant Professor with the University of Jor-dan, King Abdullah II School for Information Technology, Computer Information Systems Department. Dr. Marwan holds a B.Sc in Computer Information Systems (Al-Hussein Bin Talal University, 2006) and a M.Sc. in Information Systems (The University of Jordan, 2011), and a Ph.D in Computer Science (The University of Leeds, 2018). He is currently the Dean Assistant for Automated exams at the Univer-sity of Jordan. His current areas of interest include: Knowledge Graphs, Data Explo-ration, and Databases

Ammar Huneiti, The University of Jordan

Ammar M. Huneiti is currently a Professor with the University of Jordan, King Abdullah II School for Information Technology, Computer Information Systems Department. Prof. Ammar holds a B.Sc in Computer Science (University of Wales College of Cardiff, 1991) and a M.Sc. in Information Systems Technologies (The University of Wales College of Cardiff, 1992), and a Ph.D in Intelligent Information Systems (Cardiff University, 2004). He served as Vice Dean of KASIT during 2015-2016. His current areas of interest include: Intelligent Information Systems, Data Mining, Performance Support Systems, Multimedia, Geographic Information Sys-tems, Spatial Databases, Adaptive Hypermedia.

Rawan Shahin, The University of Jordan

M.Sc. students at The University of Jordan, King Abdullah II School for Information Technology, Computer Science.

Abeer Abu Zayed, The University of Jordan

are M.Sc. students at The University of Jordan, King Abdullah II School for Infor-mation Technology, Computer Science.

Razan Al-Dibsi, The University of Jordan

M.Sc. students at The University of Jordan, King Abdullah II School for Information Technology, Computer Science.

Downloads

Published

2020-08-14

How to Cite

Adwan, O. Y., Al-Tawil, M., Huneiti, A., Shahin, R., Abu Zayed, A., & Al-Dibsi, R. (2020). Twitter Sentiment Analysis Approaches: A Survey. International Journal of Emerging Technologies in Learning (iJET), 15(15), pp. 79–93. https://doi.org/10.3991/ijet.v15i15.14467

Issue

Section

Papers